The Technology Session provides an opportunity for speakers from academia, industry, and other sectors to give a 10-minute summary of new technologies or approaches under development in their research groups. Presentations include descriptions of new equipment for measuring plant traits as well as new approaches for the analysis of phenomics datasets. Some speakers are invited, others are selected from submitted abstracts.

5:30 PM -  5:40 PM             William Salter (School of Life and Environmental Sciences, Sydney Institute of Agriculture, The University of Sydney) -- Tackling the physiological phenotyping bottleneck with low-cost, enhanced-throughput, do-it-yourself gas exchange and ceptometry

  • Phenotyping bottlenecks
    • Traditional methods are expensive
    • New high throughput methods are still unreliable due to their infancy
  • Octoflux
    • High throughput, low cost gas exchange
    • Initially designed for wheat
    • 8 leaf chambers
    • Cost of ~$31k USD
  • Parbar
    • Low cost light measurement
    • 50 photodiodes
    • Weatherproof
  • Pardot

 

5:40 PM - 5:50 PM            Jasenka French (Cibo Technologies) -- Application of Crop Phenotyping to Computation Agronomy at CiBO Speaker has asked that viewers not tweet or take notes on her talk. 

 

5:50 PM - 6:00 PM            Zheng Xu (University of Nebraska-Lincoln) -- CT image-based Segmentation and Reconstruction of Root Systems by Machine Learning and Computational Methods

  • Root phenotyping using X-Ray systems
  • Problem is the segmentation of the root from the soil, as their intensities in the images overlap.
  • New algorithm, with good accuracy and computation time
    • Tested on cassava roots

 

6:00 PM - 6:10 PM             Grégoire Hummel (Phenospex B.V.) -- PlantEye F500: combine 3D and multispectral information in one sensor

  • Phenospex is a company that has biologist, physicists, engineers, …
  • Design sensors really designed for plants
  • Planteye F500
    • Combines 3D reconstruction and hyperspectral measurements
    • User can select 4 wavelength that can be mounted on the device
  • DualScan = dual sensors to eliminate hidden parts of the plant
  • Phena = Pipeline for the data analysis

 

6:10 PM - 6:20 PM             Larry York (Noble Research Institute) -- RhizoVision-Crown: An open hardware and software phenotyping platform for root crowns using a backlight, a machine vision camera, and a new C++ image analysis program

  • Root crown phenotyping
  • Shovelomics: excavation -> washing -> imaging
  • Phenotyping box: back light + camera -> directly good contrast
  • Cheap component: total price about 1000€
  • Image analysis pipeline open source in C++
    • Classic measurments for root crowns (convexhull, skeleton)
  • Possible to have a multiple perspective system, with 5 camera.

 

  • Shovelomics paper:
    • Trachsel S, Kaeppler SM, Brown KM, Lynch JP. Shovelomics: high throughput phenotyping of maize (Zea mays L.) root architecture in the field. Plant Soil. Kluwer Academic Publishers; 2010;341: 75–87. Available: http://www.springerlink.com/index/10.1007/s11104-010-0623-8
    • Colombi T, Kirchgessner N, Le Marié CA, York LM, Lynch JP, Hund A. Next generation shovelomics: set up a tent and REST. Plant Soil. Kluwer Academic Publishers; 2015; Available: http://link.springer.com/10.1007/s11104-015-2379-7
    • Bucksch A, Burridge J, York LM, Das A, Nord E, Weitz JS, et al. Image-based high-throughput field phenotyping of crop roots. Plant Physiol. 2014;166: 470–486. doi:10.1104/pp.114.243519

 

6:20 PM - 6:30 PM             Blake Joyce (CyVerse, BIO5 Institute, University of Arizona) -- Image Analysis using CyVerse

  • NSF funded project
    • Connect scientist to share data and perfom analysis
    • 50 000++ users
  • Genomes to Fields initiative
    • Project across many group, many states
    • Sciverse (and cyberinfrastructure in general) make it possible to collaborate across sites
  • CyVerse BisQue
    • Image analysis platform hosted on Cyverse
  • Planteome image analysis in Bisque
    • Used the database of image from Planteome, together with the planteome ontologies and use that for machine learning training.
  • Democratisation of machine learning
    • Connoisseur in Bisque
  • Literature
    • Merchant N, Lyons E, Goff S, Vaughn M, Ware D, Micklos D, et al. The iPlant Collaborative: Cyberinfrastructure for Enabling Data to Discovery for the Life Sciences. PLoS Biol. 2016;14: e1002342. doi:10.1371/journal.pbio.1002342
    • Kvilekval K, Fedorov D, Obara B, Singh A, Manjunath BS. Bisque: a platform for bioimage analysis and management. Bioinformatics. Oxford University Press; 2010;26: 544–552. Available: http://bioinformatics.oxfordjournals.org/cgi/doi/10.1093/bioinformatics/btp699

 

 

6:30 PM - 6:40 PM             Oliver Scholz (Fraunhofer Development Center X-Ray Technology) -- Phenotyping for Plant Breeding using 3D Sensors and a Generic 3D Leaf Model

  • 3D data of shoot and leaves
  • High quality point cloud data
  • The phenotyping data is coupled with a geometric leaf model
    • About 20 meaningfull parameters (width, length, curvature, ...) could be extracted from the fitted model
    • Could be seen a data reduction techniques (down to the number of parameters)
    • Fitting is done by minimizing the difference between the 3d data and the model
    • Model will probably be open source.

 

6:40 PM - 6:50 PM             James Bunce (PP Systems) -- High Throughput Photosynthesis Characterization in C3 plants

  • Single point leaf gas exchange measurements are not always physiological relevant (“what is happening next to it?”)
  • A vs Ci curves require 10 points per leaf and is slow (20-30 min per leaf)
  • Faster system

 

6:50 PM - 7:00 PM            Eric Rogers (Hi fidelity Genetics) --In situ phenotyping of root architecture in field

  • Yield volatility -  linked to water availability
  • Key to yield stability
  • Deeper penetration
  • RootTracker -  sensors arranged in a geometric row
  • Measure the resistance and capacitance in real time, that will be influenced by the contact / presence of roots
  • Validated by Xray imaging data
  • Currently deployed in the field
    • Collect data every 2 min, for the entire season
  • Can collect number of root detections and root growth rates
  • Possible to extrapolate average root density along the depth profile
  • Applications
    • Seedling establishment
    • Root architecture optimisation
    • Sensing soil properties

7:00 PM - 7:10 PM            Bruce Schnicker (The Climate Corporation) -- Leveraging Sensors, Probes and Drones to Enable Data Driven Decisions for Farmers

  • Data is transforming every major industry, including agriculture
  • Climate FieldView
    • Decision tool for farmer based on different data layers (sensors, probes, drones)
    • Include machine learning to improve the different pipelines
    • Example: disease risk modelling, based on sensors data and machine learning models